Building reliable agents under uncertainty.
- ๐งโ๐ฌ Ph.D. researcher at University of Electro-Communications (UEC), Tokyo (Apr 2024 โ 2026)
- ๐ฏ Working on Reinforcement Learning, with current focus on plasticity, world models, multi-agent RL, and real-system deployment
- ๐ JST Next-Generation Researcher (2025 โ 2027)
- ๐ผ Past: RL Algorithm Engineer @ InspirAI ยท RL Research Intern @ Baidu
- โ๏ธ I write technical notes on Zhihu โ 10K+ followers
- Plasticity-Aware Mixture of Experts for Learning Under QoE Shifts in Adaptive Video Streaming โ IEEE TMM, 2026
- A Survey on DRL based UAV Communications and Networking โ IEEE COMST, 2025 (co-authored)
- Understanding World Models through Multi-Step Pruning Policy via Reinforcement Learning โ Information Sciences, 2024
โ Full list on Google Scholar